Merge pull request nf-core#1223 from grantn5/add_cnvkit_genemetrics

Add cnvkit genemetrics
grantn5 · Oct 16, 2023 · c9bff2e · c9bff2e
2 parents 7450af9 + 9ea1aad
commit c9bff2e
Show file tree

Hide file tree

Showing 8 changed files with 118 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- [#1113](https://github.com/nf-core/sarek/pull/1113) - Adding CNVkit genemetrics module
 - [#1193](https://github.com/nf-core/sarek/pull/1193) - Adding support for Sentieon's DnaScope for germline variant-calling including joint-germline
 - [#1271](https://github.com/nf-core/sarek/pull/1271) - Back to dev
 

diff --git a/conf/base.config b/conf/base.config
@@ -70,6 +70,10 @@ process {
         cpus            = { check_max( 24 * task.attempt, 'cpus' ) }
         memory          = { check_max( 30.GB * task.attempt, 'memory' ) }
     }
+    withName:'CNVKIT_BATCH' {
+        label           = "process_high"
+        memory          = { check_max( 36.GB * task.attempt, 'memory' ) }
+    }
     withName: 'GATK4_MARKDUPLICATES|GATK4_MARKDUPLICATESSPARK' {
         cpus           = { check_max( 6 * task.attempt, 'cpus' ) }
         memory         = { check_max( 30.GB * task.attempt, 'memory' ) }

diff --git a/conf/modules/cnvkit.config b/conf/modules/cnvkit.config
@@ -47,4 +47,14 @@ process {
             pattern: "*{bed,cnn,cnr,cns,pdf,png}"
         ]
     }
+    // CNVKIT
+    withName: 'CNVKIT_GENEMETRICS' {
+        ext.prefix       = { "${cnr.baseName}.genemetrics" }
+        ext.when         = { params.tools && params.tools.split(',').contains('cnvkit') }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/cnvkit/${meta.id}/" },
+            pattern: "*{tsv}"
+        ]
+    }
 }
diff --git a/docs/output.md b/docs/output.md
@@ -717,8 +717,9 @@ The file `<tumorsample_vs_normalsample>.cnvs.txt` contains all segments predicte
   - file containing copy number segment information
 - `<sample>.call.cns`
   - file containing copy number segment information
-
-</details>
+- `<sample>.genemetrics.tsv`
+  - file containing per gene copy number information (if input files are annotated)
+  </details>
 
 <details markdown="1">
 <summary>Output files for tumor/normal samples</summary>
@@ -745,6 +746,8 @@ The file `<tumorsample_vs_normalsample>.cnvs.txt` contains all segments predicte
   - file containing copy number segment information
 - `<tumorsample>.call.cns`
   - file containing copy number segment information
+- `<tumorsample>.genemetrics.tsv`
+  - file containing per gene copy number information (if input files are annotated)
   </details>
 
 #### Control-FREEC

diff --git a/modules.json b/modules.json
@@ -70,6 +70,11 @@
                         "git_sha": "3b63e1df297ef474b0070aa5fabb30d732173671",
                         "installed_by": ["modules"]
                     },
+                    "cnvkit/genemetrics": {
+                        "branch": "master",
+                        "git_sha": "3b63e1df297ef474b0070aa5fabb30d732173671",
+                        "installed_by": ["modules"]
+                    },
                     "cnvkit/reference": {
                         "branch": "master",
                         "git_sha": "3b63e1df297ef474b0070aa5fabb30d732173671",

diff --git a/modules/nf-core/cnvkit/genemetrics/main.nf b/modules/nf-core/cnvkit/genemetrics/main.nf
diff --git a/modules/nf-core/cnvkit/genemetrics/meta.yml b/modules/nf-core/cnvkit/genemetrics/meta.yml
diff --git a/subworkflows/local/bam_variant_calling_cnvkit/main.nf b/subworkflows/local/bam_variant_calling_cnvkit/main.nf
@@ -5,6 +5,7 @@
 // A when clause condition is defined in the conf/modules.config to determine if the module should be run
 
 include { CNVKIT_BATCH } from '../../../modules/nf-core/cnvkit/batch/main'
+include { CNVKIT_GENEMETRICS } from '../../../modules/nf-core/cnvkit/genemetrics/main'
 
 workflow BAM_VARIANT_CALLING_CNVKIT {
     take:
@@ -15,11 +16,16 @@ workflow BAM_VARIANT_CALLING_CNVKIT {
     reference           // channel: [] cnn
 
     main:
+    versions = Channel.empty()
     generate_pon = false
 
     CNVKIT_BATCH(cram, fasta, fasta_fai, targets, reference, generate_pon)
 
-    versions = CNVKIT_BATCH.out.versions
+    ch_genemetrics = CNVKIT_BATCH.out.cnr.join(CNVKIT_BATCH.out.cns).map{ meta, cnr, cns -> [meta, cnr, cns[2]]}
+    CNVKIT_GENEMETRICS(ch_genemetrics)
+
+    versions = versions.mix(CNVKIT_BATCH.out.versions)
+    versions = versions.mix(CNVKIT_GENEMETRICS.out.versions)
 
     emit:
     versions // channel: [ versions.yml ]